Rostral and caudal prefrontal contribution to creativity: a meta-analysis of functional imaging data

Abstract

Creativity is of central importance for human civilization, yet its neurocognitive bases are poorly understood. The aim of the present study was to integrate existing functional imaging data by using the meta-analysis approach. We reviewed 34 functional imaging studies that reported activation foci during tasks assumed to engage creative thinking in healthy adults. A coordinate-based meta-analysis using Activation Likelihood Estimation (ALE) first showed a set of predominantly left-hemispheric regions shared by the various creativity tasks examined. These regions included the caudal lateral prefrontal cortex (PFC), the medial and lateral rostral PFC, and the inferior parietal and posterior temporal cortices. Further analyses showed that tasks involving the combination of remote information (combination tasks) activated more anterior areas of the lateral PFC than tasks involving the free generation of unusual responses (unusual generation tasks), although both types of tasks shared caudal prefrontal areas. In addition, verbal and non-verbal tasks involved the same regions in the left caudal prefrontal, temporal, and parietal areas, but also distinct domain-oriented areas. Taken together, these findings suggest that several frontal and parieto-temporal regions may support cognitive processes shared by diverse creativity tasks, and that some regions may be specialized for distinct types of processes. In particular, the lateral PFC appeared to be organized along a rostro-caudal axis, with rostral regions involved in combining ideas creatively and more posterior regions involved in freely generating novel ideas.

Keywords: creative thinking; creativity; divergent thinking; functional imaging; insight problem solving; meta-analysis; originality; semantic associations.

Figure 1

ALE map of all foci, thresholded at a whole-brain cluster-level corrected p < 0.05. Activations are displayed on the surface rendering of the Colin27 template (Holmes et al., 1998) in the MNI space.

Figure 2

(A) ALE maps of combination task foci (in cyan) and generation task foci (in red). Overlaps between maps are shown in black. All maps were thresholded at a whole-brain cluster-level corrected p < 0.05. (B) ALE maps resulting from contrast studies of combination vs. generation tasks foci (in cyan) and generation vs. combination task foci (in red). These contrast maps were thresholded at a whole-brain FDR corrected p < 0.05. In (A,B), ALE maps are displayed on a surface rendering of the Colin27 template (Holmes et al., 1998) in the MNI space.

Figure 3

(A). ALE maps of verbal task foci (in purple) and non-verbal task foci (in orange). Overlaps between maps are shown in red. All maps were thresholded at a whole-brain cluster-level corrected p < 0.05. (B). ALE maps resulting from contrast studies of verbal vs. non-verbal task foci (in purple) and non-verbal vs. verbal task foci (in orange). These contrast maps were thresholded at a whole-brain FDR corrected p < 0.05. In (A,B), ALE maps are displayed on a surface rendering of the Colin27 template (Holmes et al., 1998) in the MNI space.